INDEX

Explanations

references to legal or court-related terms and proceedings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Theſe

-1.05

Efq

-1.03

 Monfieur

-1.03

 ―――――

-0.96

 utafitiHapana

-0.95

MethodManager

-0.94

 iſt

-0.93

$_"

-0.92

 NDEBUG

-0.92

 itſelf

-0.92

POSITIVE LOGITS

0.48

0.46

0.45

pertory

0.45

0.44

PosX

0.43

0.42

II

0.41

Activations Density 0.769%

references to legal or court-related terms and proceedings

No Comments

No Known Activations